{"id":"https://openalex.org/W4417201844","doi":"https://doi.org/10.1109/lcomm.2025.3642793","title":"VT-FSC: Vision-Tactile Fusion Semantic Communication for Remote Embodied Intelligence","display_name":"VT-FSC: Vision-Tactile Fusion Semantic Communication for Remote Embodied Intelligence","publication_year":2025,"publication_date":"2025-12-10","ids":{"openalex":"https://openalex.org/W4417201844","doi":"https://doi.org/10.1109/lcomm.2025.3642793"},"language":null,"primary_location":{"id":"doi:10.1109/lcomm.2025.3642793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcomm.2025.3642793","pdf_url":null,"source":{"id":"https://openalex.org/S147316732","display_name":"IEEE Communications Letters","issn_l":"1089-7798","issn":["1089-7798","1558-2558","2373-7891"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Rui Xu","orcid":"https://orcid.org/0009-0006-0391-9890"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xu","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","School of Computer Science, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0009-0006-0391-9890","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079716972","display_name":"Yuanhang He","orcid":"https://orcid.org/0000-0002-0313-8297"},"institutions":[{"id":"https://openalex.org/I1302611135","display_name":"Ministry of Public Security of the People's Republic of China","ror":"https://ror.org/00bt9we26","country_code":"CN","type":"government","lineage":["https://openalex.org/I1302611135"]},{"id":"https://openalex.org/I4210124847","display_name":"National Engineering Research Center of Electromagnetic Radiation Control Materials","ror":"https://ror.org/02k4dcs46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210124847"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanhang He","raw_affiliation_strings":["National Key Laboratory of Security Communication, Chengdu, China","National Key Laboratory of Security Communication, Chengdu, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Security Communication, Chengdu, China","institution_ids":["https://openalex.org/I1302611135"]},{"raw_affiliation_string":"National Key Laboratory of Security Communication, Chengdu, PR China","institution_ids":["https://openalex.org/I4210124847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007267530","display_name":"Gaolei Li","orcid":"https://orcid.org/0000-0003-3913-5001"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaolei Li","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","School of Computer Science, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0003-3913-5001","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405884","display_name":"Chaofeng Zhang","orcid":"https://orcid.org/0000-0002-1042-1541"},"institutions":[{"id":"https://openalex.org/I74640424","display_name":"Advanced Institute of Industrial Technology","ror":"https://ror.org/04f9apy08","country_code":"JP","type":"education","lineage":["https://openalex.org/I74640424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chaofeng Zhang","raw_affiliation_strings":["Advanced Institute of Industrial Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1042-1541","affiliations":[{"raw_affiliation_string":"Advanced Institute of Industrial Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I74640424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391361","display_name":"Jianhua Li","orcid":"https://orcid.org/0000-0002-6831-3973"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Li","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","School of Computer Science, Shanghai Jiao Tong University, China"],"raw_orcid":"https://orcid.org/0000-0002-6831-3973","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18737309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"582","last_page":"586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.16009999811649323,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.16009999811649323,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10338","display_name":"Advanced Sensor and Energy Harvesting Materials","score":0.08030000329017639,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.06650000065565109,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6029000282287598},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5875999927520752},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5649999976158142},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.49309998750686646},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4848000109195709},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.43700000643730164},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3885999917984009},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38830000162124634},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.36880001425743103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8629000186920166},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6029000282287598},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5649999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4848000109195709},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.475600004196167},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4551999866962433},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3666999936103821},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.34439998865127563},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C201638289","wikidata":"https://www.wikidata.org/wiki/Q457396","display_name":"Ambient intelligence","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.31470000743865967},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.30070000886917114},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcomm.2025.3642793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcomm.2025.3642793","pdf_url":null,"source":{"id":"https://openalex.org/S147316732","display_name":"IEEE Communications Letters","issn_l":"1089-7798","issn":["1089-7798","1558-2558","2373-7891"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310316002","host_organization_name":"IEEE Communications Society","host_organization_lineage":["https://openalex.org/P4310316002","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Communications Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Communications Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4664115551","display_name":null,"funder_award_id":"62202303","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5875462336","display_name":null,"funder_award_id":"62572314","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7047364517","display_name":null,"funder_award_id":"62471301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2808560727","https://openalex.org/W4386065848","https://openalex.org/W4391468259","https://openalex.org/W4391677749","https://openalex.org/W4392386187","https://openalex.org/W4394897000","https://openalex.org/W4399426488","https://openalex.org/W4401504616","https://openalex.org/W4402951629","https://openalex.org/W4403780901","https://openalex.org/W4407638842","https://openalex.org/W4408442081","https://openalex.org/W4411599731","https://openalex.org/W4414165644","https://openalex.org/W4416294405"],"related_works":[],"abstract_inverted_index":{"Remote":[0],"embodied":[1,70,178],"intelligence":[2,71,179],"relies":[3],"on":[4],"the":[5,82,111,116,120,141,161],"seamless":[6],"transmission":[7],"of":[8,48,163],"rich":[9],"multi-modal":[10],"sensory":[11],"information,":[12],"particularly":[13],"vision":[14],"and":[15,26,34,51,78,88,108,119,129,154,172],"touch,":[16],"to":[17,21,113,150],"enable":[18],"intelligent":[19],"agents":[20],"collaboratively":[22],"perceive,":[23],"interact":[24],"with,":[25],"manipulate":[27],"physical":[28],"environments.":[29],"However,":[30],"transmitting":[31],"such":[32],"high-dimensional":[33],"heterogeneous":[35],"data":[36,90],"over":[37],"wireless":[38,106],"channels":[39,107],"in":[40,46,140,166],"real":[41],"time":[42],"poses":[43],"substantial":[44],"challenges":[45],"terms":[47],"bandwidth,":[49],"latency,":[50],"semantic":[52,63,80,95,169],"integrity.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,92],"novel":[60],"vision-tactile":[61],"fusion":[62,77],"communication":[64],"(VT-FSC)":[65],"framework":[66,165],"tailored":[67],"for":[68,176],"remote":[69,177],"applications.":[72,180],"By":[73],"leveraging":[74],"cross-modal":[75],"feature":[76],"attention-guided":[79],"compression,":[81],"proposed":[83],"system":[84],"transforms":[85],"raw":[86],"visual":[87,117],"tactile":[89,121],"into":[91],"unified":[93],"low-dimensional":[94],"representation.":[96],"This":[97],"compact":[98],"representation":[99],"is":[100],"then":[101],"robustly":[102],"transmitted":[103],"through":[104],"noisy":[105],"decoded":[109],"at":[110],"receiver":[112],"reconstruct":[114],"both":[115],"scene":[118],"signal":[122],"accurately.":[123],"To":[124],"ensure":[125],"perceptual":[126,174],"alignment,":[127],"encoder":[128],"decoder":[130],"are":[131],"jointly":[132],"optimized":[133],"via":[134],"human-in-the-loop":[135],"feedback":[136],"mechanisms.":[137],"Experimental":[138],"results":[139],"multi-model":[142],"dataset":[143],"show":[144],"that":[145],"our":[146,164],"method":[147],"achieves":[148],"up":[149],"15%":[151],"higher":[152],"ST-SIM":[153],"47%":[155],"lower":[156],"RMSE":[157],"than":[158],"baselines,":[159],"validating":[160],"effectiveness":[162],"achieving":[167],"high":[168],"compression":[170],"rates":[171],"accurate":[173],"reconstruction":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-10T00:00:00"}